Blog
Notes on AI engineering
Practical articles on AI agents, RAG, LLM integrations, evals and security — from real projects, no fluff.
An LLM without a GPU: serving Qwen2.5-0.5B on a plain x86 CPU with FastAPI and Docker
A walkthrough of our open-source project for running a small language model on an ordinary CPU server: an offline Docker image with baked-in weights, a FastAPI chat API with streaming, real latency and memory numbers, and what is still missing before production.
AI engineer roadmap 2026: skills a software developer needs to build LLM products
What an AI engineer actually does, how the role differs from ML engineering, and a step-by-step learning roadmap for developers: LLM APIs, prompting, RAG, agents, evals, observability, security and production skills — with resources and project ideas.
How to choose an LLM for your product: benchmarks, real evals, cost, latency and lock-in
A practical framework for selecting language models: what public benchmarks like SWE-bench, LMArena and HELM do and don't tell you, contamination, building a task-specific eval, cost and latency trade-offs, open vs closed models and avoiding lock-in.
Privacy for LLM applications: GDPR, personal data in prompts, PII redaction and vendor choices
A developer's guide to personal data in AI features: GDPR principles applied to LLMs, data flows and DPAs, retention and training settings, PII redaction, RAG access control, logs, data subject rights and Ukrainian law.
Document processing with LLMs: extracting data from invoices, contracts and scans into your ERP
How to build an intelligent document processing pipeline with vision-capable LLMs: PDF and scan handling, schema-based extraction, validation, confidence and human review, ERP integration with Odoo, accuracy metrics and costs.